© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 85244
    Prev
    Next
    INDEX
    Explanations

    prior to

    np_acts-logits-general · gemini-2.5-flash-lite

    features, risks, deceleration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     sats
    0.42
     uncountable
    0.41
     jät
    0.41
     colle
    0.40
     collège
    0.40
    යේ
    0.40
     persisting
    0.40
     impactful
    0.39
    鳎
    0.39
    ೊಂಡು
    0.39
    POSITIVE LOGITS
     काबू
    0.45
     আরো
    0.43
     அதே
    0.43
     dezelfde
    0.43
     அந்த
    0.43
    landmarks
    0.43
    还
    0.43
     મતદાન
    0.42
     pedestrians
    0.42
    ?}
    0.41
    Activations Density 0.000%

    No Known Activations